Logo
Deploy Now

SaaS Alternative

Relevance AI

Categories

Self-Hosted Developer Tools AI Automation LLM RAG Agents Low Code

Stars

153,630

Forks

9,925

Watchers

541

Developer links

Last Updated: 08-25-2026 01:43 AM (UTC)

Langflow

Langflow turns LLM application development into a visual canvas where every node maps to a real LangChain primitive (chains, agents, retrievers, memory, vector stores, and tools) that teams wire together without writing integration boilerplate. The platform supports 15+ LLM provider components including OpenAI, Anthropic, Google Gemini, Mistral, Groq, Cohere, Azure OpenAI, HuggingFace, and Ollama for fully local inference, with LiteLLM proxying to over 100 additional providers through a single OpenAI-compatible endpoint. Vector database integrations cover Pinecone, Weaviate, Chroma, Qdrant, Astra DB, OpenSearch, FAISS, and Milvus, while built-in Knowledge Bases introduced in version 1.8 allow RAG pipelines without any external vector service. Multi-agent orchestration enables agent-to-agent communication with conversation management, persistent Memory Bases for cross-session context retrieval, and step-by-step reasoning visibility in the interactive Playground. Every flow automatically becomes a callable REST API endpoint via the /run route and an MCP server exposable to Claude Desktop, Cursor, or any MCP-compatible client. Every component is a real Python class that developers can customize, extend, or replace, while Extension Bundles package third-party integrations as independent pip packages for modular installation. Tool integrations include web search, Slack, Gmail, Google Drive, GitHub, and custom REST API calls. Docker deployment with PostgreSQL persistence runs on port 7860. Backed by 153,000+ stars and DataStax. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Langflow
Langflow
Langflow
Langflow
Langflow

Benefits

  • Visual Agent Building Canvas
  • Drag-and-drop LangChain primitives onto a canvas to build agents, RAG pipelines, and multi-step chains without writing integration boilerplate, then test immediately in the interactive Playground.
  • Universal LLM Provider Support
  • Connect to OpenAI, Anthropic, Google Gemini, Mistral, Groq, Cohere, Ollama, and over 100 additional providers through LiteLLM, swapping models without changing flow logic.
  • Automatic API and MCP Exposure
  • Every flow automatically becomes a callable REST API endpoint and an MCP server, enabling integration into any application framework or MCP-compatible client like Claude Desktop.
  • Python-Native Component Extensibility
  • Every canvas node is a real Python class that developers can customize, extend, or replace with custom components, with Extension Bundles packaging third-party integrations as independent pip packages.

Features

  • Multi-Agent Orchestration
  • Build agent-to-agent communication flows with conversation management, persistent Memory Bases for cross-session context, and step-by-step reasoning visibility.
  • Vector Database Integrations
  • Connect to Pinecone, Weaviate, Chroma, Qdrant, Astra DB, OpenSearch, FAISS, and Milvus, or use built-in Knowledge Bases without external services.
  • Interactive Playground
  • Test and refine flows in real time with step-by-step agent reasoning, tool selection visibility, and multi-model response comparison.
  • Built-In Tool Library
  • Pre-built integrations for web search, Slack, Gmail, Google Drive, GitHub, custom REST API calls, and any MCP-compatible tool server.
  • Docker and PostgreSQL Deployment
  • Deploy via Docker Compose with persistent PostgreSQL storage, configurable environment variables, and custom component loading at startup on port 7860.